Matthieu Futeral

multimodal machine translation (2) few-shot learning (1) embedding learning (1) in-context learning (1) prosody analysis (1) dependency parsing (1) multimodal learning (1) ambiguity resolution (1) visual grounding (1) speaker recognition (1) cross-modal representation (1) model training (1) multimodal large language model (1) classifier-free guidance (1) universal dependency (1) embedding model (1) multilingual corpus (1) audio generation (1) speech generation (1) prosody modeling (1)